• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.161-177
• /
• 2019

In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1254-1271
• /
• 2018

Keyphrase extraction is one of fundamental natural language processing (NLP) tools to improve many text-mining applications such as document summarization and clustering. In this paper, we propose to use two novel techniques on the top of the state-of-the-art keyphrase extraction methods. First is the anti-patterns that aim to recognize non-keyphrase candidates. The state-of-the-art methods often used the rich feature set to identify keyphrases while those rich feature set cover only some of all keyphrases because keyphrases share very few similar patterns and stylistic features while non-keyphrase candidates often share many similar patterns and stylistic features. Second one is to use the dependency graph instead of the word co-occurrence graph that could not connect two words that are syntactically related and placed far from each other in a sentence while the dependency graph can do so. In experiments, we have compared the performances with different settings of the graphs (co-occurrence and dependency), and with the existing method results. Finally, we discovered that the combination method of dependency graph and anti-patterns outperform the state-of-the-art performances.

• Journal of the Korea Safety Management & Science
• /
• v.13 no.2
• /
• pp.231-241
• /
• 2011

Business processes are often of long duration, and include internal worker's decision making, which makes business processes to be exposed to many exceptional situations. These properties of business processes makes it difficult to guarantee successful termination of business processes at the design phase. The behavioral properties of business processes mainly depends on the data aspects of business processes. To formalize the data aspect of process modeling, this paper proposes a graph-based model, called Data Dependency Graph (DDG), constructed from dependency relationships specified between business data. The paper also defines a mechanism of describing a set of mapping rules that generates a process model semantically equivalent to a DDG, which is accomplished by allocating data dependencies to component activities.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.5
• /
• pp.1107-1116
• /
• 2014

In this paper, we review recent developments in network analysis using the graph theory, and introduce ongoing research area with relevant theoretical results. In specific, we introduce basic notations in graph, and conditional and marginal approach in constructing the adjacency matrix. Also, we introduce the Marcenko-Pastur law, the Tracy-Widom law, the white Wishart distribution, and the spiked distribution. Finally, we mention the relationship between degrees and eigenvalues for the detection of hubs in a network.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.7
• /
• pp.1805-1816
• /
• 1999

This paper presents the Module Class Dependency Graph for expressing the dependency relations between classes effectively. The object-oriented language is developed independently at design time, and consists of relationship between classes. Therefore we need to consider these characteristics of independence, and to express effectively the relation of classes which is existed in class hierarchy. In the System Dependence Graph and Class Dependence Graph, the relationship of classes is not expressed. To express the class relationship, we propose the Module Class Dependence Graph, and we verify the effectiveness of this method applying to object constructor, inheritance relationship and dynamic binding. Also, we presents the expressing method of parameter to identify the member data of classes. Using this Module Class Dependency Graph, we can analyze the relationship of module class correctly at design time. This method can be applied to reverse engineering, testing, visualization and other various fields to analyze system.

• ETRI Journal
• /
• v.32 no.3
• /
• pp.486-489
• /
• 2010

This letter presents a modified Pegasos algorithm for graph-based dependency parsing. We show that the modified Pegasos algorithm outperforms the margin infused relaxed and passive aggressive algorithms in three languages.

• Proceedings of the Safety Management and Science Conference
• /
• 2011.04a
• /
• pp.329-338
• /
• 2011

Business processes are often of long duration, and include internal worker's decision making, which makes business processes to be exposed to many exceptional situations. These properties of business processes makes it difficult to design processes to support uncertainties from internal or external environments. The behavioral properties of business processes mainly depends on the data aspects of business processes. To formalize the data aspect of process modeling, this paper proposes a graph-based model, called Data Dependency Graph (DDG), constructed from dependency relationships specified between business data. The paper also defines a mechanism of describing a set of mapping rules that generates a process model semantically equivalent to a DDG, which is accomplished by allocating data dependencies to component activities.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.10
• /
• pp.2567-2574
• /
• 1998

Many software engineering tools and techniques rely on fraphic representations of software, such as control flow graphs, program dependene graphs, or system dependence graphs. Existing graphic representations for object-oriented programs are compkicated, reduplicated. We thus propose a new graphic representation for object-oriented programs. Object-oriented Program Dependency Graph (OPDG). An OPDG consists of class dependence graph, class hierarchy graph and procedure dependence graph. Other features of OPDG are (1) the representation is compact; (2) the representation is easy to extend for the incremental development of a program; and (3) the repreesentation can be extended to provide dynamic information.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.11a
• /
• pp.78-81
• /
• 2010

In this paper, we propose an efficient and effective selective protection scheme to SVC that exploit the propagation of protection effect by protecting significant frames that can give the maximum visual quality degradation. We model SVC dependency coding structure as a directed acyclic graph which is characterized with an estimated visual quality value as the attribute at each node. The estimated visual quality is calculated by using our model based on the proportions of intra- and inter-predicted MBs, amounts of residual, and estimated visual quality of reference frames. The proposed selective protection scheme traverses the graph to find optimal protection paths that can give maximum visual quality degradation. Experimental results show that the proposed selective protection scheme reduces the required number of frames to be protected by 46.02% compared to the whole protection scheme and 27.56% compared to the layered protection scheme.

• Korean Journal of Construction Engineering and Management
• /
• v.22 no.1
• /
• pp.106-115
• /
• 2021

Classifying work trades using images can serve an important role in a multitude of advanced applications in construction management and automated progress monitoring. However, images obtained from work sites may not always be clean. Defective images can damage an image classifier's accuracy which gives rise to a needs for a method to enhance a work trade image classifier's performance. We propose a method that uses work dependency information to aid image classifiers. We show that using work dependency can enhance the classifier's performance, especially when a base classifier is not so great in doing its job.